© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6606
    Prev
    Next
    INDEX
    Explanations

    academic references, specifically focusing on PhD theses and dissertations in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     we
    -0.56
    OGND
    -0.51
     feature
    -0.50
    +#+#
    -0.49
     features
    -0.49
     We
    -0.47
    we
    -0.46
    Хьажоргаш
    -0.46
     ourselves
    -0.45
     WE
    -0.44
    POSITIVE LOGITS
     thesis
    0.99
    Thesis
    0.96
     Thesis
    0.94
    thesis
    0.92
    parsedMessage
    0.87
     THESIS
    0.84
    Dissertation
    0.80
    complexContent
    0.79
    sertation
    0.79
     dissertation
    0.77
    Activations Density 0.105%

    No Known Activations